Papers
arxiv:2507.23284

Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval

Published on Jul 31
· Submitted by ikodoh on Aug 6
Authors:
,
,
,

Abstract

A novel retrieval framework using bidirectional likelihood estimation with multi-modal large language models and candidate prior normalization improves text-video retrieval by reducing candidate prior bias and enhancing query-candidate relevance.

AI-generated summary

Text-Video Retrieval aims to find the most relevant text (or video) candidate given a video (or text) query from large-scale online databases. Recent work leverages multi-modal large language models (MLLMs) to improve retrieval, especially for long or complex query-candidate pairs. However, we observe that the naive application of MLLMs, i.e., retrieval based on candidate likelihood, introduces candidate prior bias, favoring candidates with inherently higher priors over those more relevant to the query. To this end, we propose a novel retrieval framework, Bidirectional Likelihood Estimation with MLLM (BLiM), which leverages both query and candidate likelihoods by training the model to generate text from a given video as well as video features from a given text. Furthermore, we introduce Candidate Prior Normalization (CPN), a simple yet effective training-free score calibration module designed to mitigate candidate prior bias in candidate likelihood. On four Text-Video Retrieval benchmarks, our BLiM equipped with CPN outperforms previous state-of-the-art models by 6.4 R@1 on average, effectively alleviating candidate prior bias and emphasizing query-candidate relevance. Our in-depth analysis across various multi-modal tasks beyond retrieval highlights the broad applicability of CPN which enhances visual understanding by reducing reliance on textual priors. Code is available at https://github.com/mlvlab/BLiM.

Community

Paper author Paper submitter

A novel retrieval framework using bidirectional likelihood estimation with multi-modal large language models and candidate prior normalization improves text-video retrieval by reducing candidate prior bias and enhancing query-candidate relevance.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.23284 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.23284 in a Space README.md to link it from this page.

Collections including this paper 1